NVIDIA GeForce GTX 1650 SUPER vs NVIDIA GeForce GTX 960 Comparison

FAQ

Q: How does the NVIDIA GeForce GTX 1650 SUPER compare to the GTX 960 in overall benchmark scores?

A: The GTX 1650 SUPER records an average benchmark score of 11047, while the GTX 960 sits at 9273. That puts the newer card roughly 19% higher in aggregate performance, and it occupies the 50th percentile among all GPUs versus the GTX 960’s 45th percentile.

Q: Which card wins in the 3DMark Steel Nomad DX12 test?

A: The GTX 1650 SUPER scores 352 in that test, while the GTX 960 scores 162. The delta is 117.3% in favor of the GTX 1650 SUPER, meaning it more than doubles the GTX 960’s result.

Q: What about compute-oriented workloads like Geekbench OpenCL?

A: The GTX 1650 SUPER posts 43875 in Geekbench OpenCL against 18925 for the GTX 960, a 131.8% advantage. The gap is even larger in Geekbench Vulkan, where the GTX 1650 SUPER scores 50519 versus 9231, a 447.3% difference.

Q: Are both cards from the same manufacturing process?

A: No. The GTX 1650 SUPER uses a 12 nm process at TSMC, while the GTX 960 uses a 28 nm process, also at TSMC. The transistor counts reflect that: 6,600 million for the GTX 1650 SUPER versus 2,940 million for the GTX 960.

Q: Do both cards have the same memory configuration?

A: No. The GTX 1650 SUPER has 4 GB of GDDR6 memory on a 128-bit bus, yielding 192.0 GB/s bandwidth. The GTX 960 has 2 GB of GDDR5 memory on the same 128-bit bus, with 112.2 GB/s bandwidth.

Q: Which card has a higher launch MSRP?

A: The GTX 960 had a launch MSRP of 199 USD, while the GTX 1650 SUPER had a launch MSRP of 159 USD. Both are now end-of-life products.

Architecture Differences

The two cards belong to different generations and architectures. The GTX 1650 SUPER is built on the Turing architecture, using the TU116 chip, and is part of the GeForce 16 generation. The GTX 960 uses the Maxwell 2.0 architecture with the GM206 chip, from the GeForce 900 series. This architectural shift brings a significant change in manufacturing process: the GTX 1650 SUPER is fabricated on a 12 nm node, while the GTX 960 uses a 28 nm node. Both are produced by TSMC, but the density improvement is stark. The GTX 1650 SUPER packs 6,600 million transistors on a 284 mm² die, giving a transistor density of 23.2M per mm². The GTX 960 contains 2,940 million transistors on a 228 mm² die, for a density of 12.9M per mm². That means the newer chip fits more than twice the transistors into a modestly larger die.

The compute resources also differ. The GTX 1650 SUPER has 1280 shading units, 80 texture mapping units, and 32 ROPs. The GTX 960 has 1024 shading units, 64 TMUs, and 32 ROPs. Neither card includes ray tracing cores or tensor cores, so both rely on traditional rasterization. Clock speeds favor the newer card as well. The GTX 1650 SUPER has a base clock of 1530 MHz and a boost clock of 1725 MHz. The GTX 960 runs at 1127 MHz base and 1178 MHz boost. Those higher clocks, combined with more shading units, produce a large throughput gap. The GTX 1650 SUPER delivers 4.416 TFLOPS of FP32 compute, while the GTX 960 delivers 2.413 TFLOPS. The GTX 1650 SUPER also supports FP16 at 8.832 TFLOPS with a 2:1 ratio, a feature not listed for the GTX 960.

Memory architecture differs as well. The GTX 1650 SUPER uses 4 GB of GDDR6 memory at 1500 MHz, with 12 Gbps effective speed. The GTX 960 uses 2 GB of GDDR5 at 1753 MHz, with 7 Gbps effective speed. Both have a 128-bit memory bus, but the newer card’s higher-speed memory gives it 192.0 GB/s of bandwidth versus 112.2 GB/s for the older card. That is a 71% bandwidth advantage. Pixel and texture rates follow the same trend. The GTX 1650 SUPER achieves 55.20 GPixel/s and 138.0 GTexel/s, while the GTX 960 manages 37.70 GPixel/s and 75.39 GTexel/s.

Power characteristics also differ. The GTX 1650 SUPER has a TDP of 100 W, while the GTX 960 has a higher TDP of 120 W. Both cards use a single 6-pin power connector and share a suggested PSU rating of 300 W. Both are dual-slot designs. The GTX 1650 SUPER measures 229 mm in length (9 inches), 111 mm in height (4.4 inches), and 35 mm in width (1.4 inches). The GTX 960 is longer at 241 mm (9.5 inches), with no height or width listed in the database.

Display outputs also differ. The GTX 1650 SUPER offers 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a. The GTX 960 provides 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.2. The API support is identical on paper: both cards support DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4.

The Verdict

The data points to a clear winner for most use cases. The GTX 1650 SUPER outperforms the GTX 960 in every head-to-head benchmark recorded in the database. It wins all three tests: 3DMark Steel Nomad DX12, Geekbench OpenCL, and Geekbench Vulkan. The average benchmark score is 11047 versus 9273, a margin of roughly 19%. The percentile ranking also favors the newer card, 50th versus 45th among all GPUs.

For users who prioritize modern API performance, the GTX 1650 SUPER is the obvious choice. Its 447.3% lead in Geekbench Vulkan suggests it handles Vulkan workloads far more efficiently than the GTX 960. The 131.8% lead in OpenCL also indicates a substantial advantage in compute-heavy tasks. For gamers targeting DX12 titles, the 117.3% advantage in 3DMark Steel Nomad reinforces the same conclusion.

The GTX 960 does have one thing going for it: a lower launch MSRP? No, actually the GTX 1650 SUPER launched at 159 USD, while the GTX 960 launched at 199 USD. The GTX 960 also has a higher TDP at 120 W compared to 100 W for the GTX 1650 SUPER, so it is less power-efficient based on the recorded specs. There is no benchmark category where the GTX 960 wins. Users with an older system that requires a 28 nm card may have no choice, but the performance data shows the GTX 1650 SUPER is superior across the board.

The GTX 960 does offer three DisplayPort outputs versus one for the GTX 1650 SUPER, which could matter for multi-monitor setups. But in raw performance, the GTX 1650 SUPER is ahead. The verdict from the database is straightforward: pick the GTX 1650 SUPER unless you specifically need the GTX 960’s DisplayPort configuration or are constrained by legacy compatibility.

Specification Differences

The following fields differ between the two cards, based on the database records:

• Chip: TU116 (GTX 1650 SUPER) versus GM206 (GTX 960)
• Architecture: Turing versus Maxwell 2.0
• Generation: GeForce 16 versus GeForce 900
• Process node: 12 nm versus 28 nm
• Transistors: 6,600 million versus 2,940 million
• Die size: 284 mm² versus 228 mm²
• Transistor density: 23.2M / mm² versus 12.9M / mm²
• Base clock: 1530 MHz versus 1127 MHz
• Boost clock: 1725 MHz versus 1178 MHz
• Memory clock: 1500 MHz (12 Gbps effective) versus 1753 MHz (7 Gbps effective)
• Memory size: 4 GB versus 2 GB
• Memory type: GDDR6 versus GDDR5
• Memory bandwidth: 192.0 GB/s versus 112.2 GB/s
• Shading units: 1280 versus 1024
• TMUs: 80 versus 64
• Pixel rate: 55.20 GPixel/s versus 37.70 GPixel/s
• Texture rate: 138.0 GTexel/s versus 75.39 GTexel/s
• FP32 performance: 4.416 TFLOPS versus 2.413 TFLOPS
• FP16 performance: 8.832 TFLOPS (2:1) versus not listed
• TDP: 100 W versus 120 W
• Length: 229 mm (9 inches) versus 241 mm (9.5 inches)
• Height: 111 mm (4.4 inches) versus not listed
• Width: 35 mm (1.4 inches) versus not listed
• Display outputs: 1x DVI, 1x HDMI 2.0, 1x DisplayPort 1.4a versus 1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.2
• Release date: 2019-11-21 versus 2015-01-21
• Predecessor: GeForce 10 versus GeForce 700
• Successor: GeForce 20 versus GeForce 10
• Launch MSRP: 159 USD versus 199 USD
• Average benchmark score: 11047 versus 9273
• Percentile vs all GPUs: 50 versus 45

Both cards share the same ROP count (32), bus interface (PCIe 3.0 x16), power connector (1x 6-pin), suggested PSU (300 W), slot width (Dual-slot), and API support (DirectX 12_1, OpenGL 4.6, Vulkan 1.4). Both are end-of-life products from NVIDIA.

Head-to-Head Benchmarks

The database contains three direct comparisons between these two cards, and the GTX 1650 SUPER wins all of them.

The largest margin appears in Geekbench Vulkan. The GTX 1650 SUPER scores 50519, while the GTX 960 scores 9231. That is a delta of 447.3% in favor of the newer card. This is a massive gap, suggesting the GTX 1650 SUPER’s Turing architecture is far more efficient at Vulkan tasks. For users running Vulkan-based games or compute applications, this difference is decisive. The GTX 960’s score is less than one-fifth of the GTX 1650 SUPER’s result.

Geekbench OpenCL shows a similar but slightly smaller advantage. The GTX 1650 SUPER records 43875, and the GTX 960 records 18925. The delta is 131.8%. This indicates that for OpenCL compute workloads, the GTX 1650 SUPER more than doubles the performance of the GTX 960. The higher shading unit count, faster clocks, and greater memory bandwidth all contribute to this result.

In 3DMark Steel Nomad DX12, the GTX 1650 SUPER scores 352 against 162 for the GTX 960, a delta of 117.3%. While this is the smallest relative advantage of the three tests, it still represents a doubling of the DX12 performance. The GTX 1650 SUPER’s 4 GB of GDDR6 memory and 192.0 GB/s bandwidth likely play a role in this improvement, as DX12 workloads often benefit from higher memory throughput.

The wins are consistent across all recorded metrics. The GTX 1650 SUPER also holds a higher average benchmark score overall, 11047 versus 9273, and a better percentile ranking. The GTX 960’s nearest rivals in the database include the GeForce GTX 465 (avg score 9294, delta -0.2%), GTX 850M (9302, -0.3%), Radeon R7 M380 (9313, -0.4%), and Radeon Vega 8 (9221, +0.6%). The GTX 1650 SUPER’s nearest rivals include the Radeon RX 550 (11075, -0.2%), two RTX PRO 6000 variants (both 11088, -0.4%), and the GeForce MX350 (10883, +1.5%). This places the GTX 1650 SUPER in a higher performance tier than the GTX 960, whose rivals are all lower-scoring parts.

The head-to-head data leaves no ambiguity. The GTX 1650 SUPER is the faster card in every recorded test, with deltas ranging from 117.3% to 447.3%. The only areas where the GTX 960 comes out ahead are physical attributes: it is longer, has a higher TDP, and offers more DisplayPort outputs. None of those factors translate into better benchmark performance.